Benjamin ChislettandGitHub c628a93a64 [Perf][Bugfix] Update dflash aux layer indexing (#40727) ...

Signed-off-by: Benjamin Chislett <bchislett@nvidia.com>

2026-05-19 20:15:57 -07:00

..

general

[Bugfix][Hybrid][NemotronH] Fix mamba_cache_mode=all + speculative decoding crash (#41233)

2026-05-18 14:54:00 +03:00

spec_decode

[Perf][Bugfix] Update dflash aux layer indexing (#40727)

2026-05-19 20:15:57 -07:00

__init__.py

[V1] Implement Cascade Attention (#11635)

2025-01-01 21:56:46 +09:00

test_hybrid_chunked_prefill.py

[ROCm][CI] Enable hybrid chunked prefill test (#38317)

2026-03-30 10:30:26 +08:00